{"id":"https://openalex.org/W2785508536","doi":"https://doi.org/10.1109/apsipa.2017.8282218","title":"Word level prosody prediction using large audiobook dataset","display_name":"Word level prosody prediction using large audiobook dataset","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2785508536","doi":"https://doi.org/10.1109/apsipa.2017.8282218","mag":"2785508536"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282218","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112223666","display_name":"Yanfeng Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yanfeng Lu","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101678004","display_name":"Chenyu Yang","orcid":"https://orcid.org/0000-0002-0346-7541"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chenyu Yang","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021872761","display_name":"Minghui Dong","orcid":"https://orcid.org/0000-0001-6543-2929"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Minghui Dong","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112223666"],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19969244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2013","issue":null,"first_page":"1268","last_page":"1273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.862205982208252},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7521119713783264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7433168888092041},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5924063920974731},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5591812133789062},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5262460112571716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5073596835136414},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.499500036239624},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.47409021854400635},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42473074793815613},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15880581736564636}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.862205982208252},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7521119713783264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433168888092041},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5924063920974731},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5591812133789062},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5262460112571716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5073596835136414},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.499500036239624},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.47409021854400635},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42473074793815613},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15880581736564636},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8282218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282218","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1875231349","https://openalex.org/W2024093103","https://openalex.org/W2055496006","https://openalex.org/W2064675550","https://openalex.org/W2124551647","https://openalex.org/W2150658333","https://openalex.org/W2181607856","https://openalex.org/W2293634267","https://openalex.org/W2598638573","https://openalex.org/W2963078821","https://openalex.org/W4390911898","https://openalex.org/W4395961412","https://openalex.org/W6631362777","https://openalex.org/W6634854370","https://openalex.org/W6639350448","https://openalex.org/W6686045668","https://openalex.org/W6696934422","https://openalex.org/W6866196433"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925","https://openalex.org/W2587342322"],"abstract_inverted_index":{"Prosody":[0],"modelling":[1,70,131],"is":[2,108,115],"an":[3,116],"essential":[4],"part":[5],"of":[6,47,97,125],"the":[7,39,69,99,104],"text-to-":[8],"speech":[9,105,126,133],"synthesis":[10,106],"system.":[11],"In":[12],"this":[13],"paper":[14],"we":[15,34],"propose":[16],"and":[17,57,92,123],"investigate":[18],"a":[19,44],"way":[20,96,118],"to":[21,27,81,119,128],"leverage":[22,120],"public":[23,48],"domain":[24,49],"audiobook":[25,50],"data":[26,51,127],"do":[28,129],"word":[29,74,85,100],"level":[30],"prosody":[31,86,101,130],"modelling.":[32],"Specifically":[33],"base":[35],"our":[36],"work":[37],"on":[38],"LibriSpeech":[40],"project,":[41],"in":[42],"which":[43],"large":[45,121],"quantity":[46,122],"from":[52,77],"LibriVox":[53],"were":[54],"processed,":[55],"selected":[56],"aligned":[58],"with":[59],"text.":[60],"We":[61],"choose":[62],"long-short-term-memory":[63],"recurrent":[64],"deep":[65],"neural":[66],"network":[67],"as":[68],"tool.":[71],"The":[72,84],"input":[73],"features":[75,87],"spread":[76],"phonetic,":[78],"through":[79],"syntactic,":[80],"semantic":[82],"layers.":[83],"include":[88],"log":[89],"F0,":[90],"energy":[91],"after-word":[93],"break.":[94],"A":[95],"incorporating":[98],"model":[102],"into":[103],"system":[107],"also":[109],"proposed.":[110],"Experiments":[111],"show":[112],"that":[113],"it":[114],"effective":[117],"variety":[124],"for":[132],"synthesis.":[134]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}